{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:03:37Z","timestamp":1764785017292,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031204968"},{"type":"electronic","value":"9783031204975"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20497-5_34","type":"book-chapter","created":{"date-parts":[[2022,12,16]],"date-time":"2022-12-16T12:09:06Z","timestamp":1671192546000},"page":"416-428","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Prompt Learning with\u00a0Cross-Modal Feature Alignment for\u00a0Visual Domain Adaptation"],"prefix":"10.1007","author":[{"given":"Jinxing","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjin","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haokai","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangxian","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuang","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangxu","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,12,17]]},"reference":[{"key":"34_CR1","doi-asserted-by":"crossref","unstructured":"Chen, J., Ngo, C.W.: Deep-based ingredient recognition for cooking recipe retrieval. In: Proceedings of the 24th ACM International Conference on Multimedia, pp. 32\u201341 (2016)","DOI":"10.1145\/2964284.2964315"},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"Chua, T.S., Tang, J., Hong, R., Li, H., Luo, Z., Zheng, Y.: Nus-wide: a real-world web image database from national university of Singapore. In: Proceedings of the ACM International Conference on Image and Video Retrieval, pp. 1\u20139 (2009)","DOI":"10.1145\/1646396.1646452"},{"key":"34_CR3","unstructured":"Chung, Y.A., Weng, W.H., Tong, S., Glass, J.: Unsupervised cross-modal alignment of speech and text embedding spaces. In: Advances in Neural Information Processing Systems 31 (2018)"},{"key":"34_CR4","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Huang, H., et al.: Unicoder: a universal language encoder by pre-training with multiple cross-lingual tasks. arXiv preprint arXiv:1909.00964 (2019)","DOI":"10.18653\/v1\/D19-1252"},{"key":"34_CR7","doi-asserted-by":"crossref","unstructured":"Iki, T., Aizawa, A.: Effect of visual extensions on natural language understanding in vision-and-language models. arXiv preprint arXiv:2104.08066 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.167"},{"key":"34_CR8","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1109\/TIP.2019.2929447","volume":"29","author":"S Jiang","year":"2019","unstructured":"Jiang, S., Min, W., Liu, L., Luo, Z.: Multi-scale multi-view deep feature aggregation for food recognition. IEEE Trans. Image Process. 29, 265\u2013276 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"34_CR9","unstructured":"Kim, W., Son, B., Kim, I.: ViLT: vision-and-language transformer without convolution or region supervision. In: International Conference on Machine Learning, pp. 5583\u20135594. PMLR (2021)"},{"key":"34_CR10","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: VisualBert: a simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)"},{"key":"34_CR11","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"34_CR12","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: VilBert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Advances in Neural Information Processing Systems 32 (2019)"},{"key":"34_CR13","doi-asserted-by":"crossref","unstructured":"Martinel, N., Foresti, G.L., Micheloni, C.: Wide-slice residual networks for food recognition. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 567\u2013576. IEEE (2018)","DOI":"10.1109\/WACV.2018.00068"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Meng, L., et al.: Learning using privileged information for food recognition. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 557\u2013565 (2019)","DOI":"10.1145\/3343031.3350870"},{"key":"34_CR15","unstructured":"Qi, D., Su, L., Song, J., Cui, E., Bharti, T., Sacheti, A.: ImageBert: cross-modal pre-training with large-scale weak-supervised image-text data. arXiv preprint arXiv:2001.07966 (2020)"},{"key":"34_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1007\/978-3-319-49409-8_35","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"B Sun","year":"2016","unstructured":"Sun, B., Saenko, K.: Deep coral: correlation alignment for deep domain adaptation. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 443\u2013450. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-49409-8_35"},{"key":"34_CR17","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: Lxmert: learning cross-modality encoder representations from transformers. arXiv preprint arXiv:1908.07490 (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"34_CR18","doi-asserted-by":"crossref","unstructured":"Tang, J., Shu, X., Li, Z., Qi, G.J., Wang, J.: Generalized deep transfer networks for knowledge propagation in heterogeneous domains (2016)","DOI":"10.1145\/2998574"},{"key":"34_CR19","doi-asserted-by":"crossref","unstructured":"Tang, J., et al.: Tri-clustered tensor completion for social-aware image tag refinement. IEEE Trans. Pattern Anal. Mach. Intell. 39(8), 1662\u20131674 (2016)","DOI":"10.1109\/TPAMI.2016.2608882"},{"key":"34_CR20","unstructured":"Tang, Z., Cho, J., Tan, H., Bansal, M.: VidLanKD: improving language understanding via video-distilled knowledge transfer. In: Advances in Neural Information Processing Systems 34 (2021)"},{"key":"34_CR21","unstructured":"Wang, J., Wang, H., Deng, J., Wu, W., Zhang, D.: EfficientcCLIP: efficient cross-modal pre-training by ensemble confident learning and language modeling. arXiv preprint arXiv:2109.04699 (2021)"},{"key":"34_CR22","doi-asserted-by":"crossref","unstructured":"Yu, F., et al.: ERNIE-ViL: knowledge enhanced vision-language representations through scene graphs. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 3208\u20133216 (2021)","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"34_CR23","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., Komodakis, N.: Wide residual networks. arXiv preprint arXiv:1605.07146 (2016)","DOI":"10.5244\/C.30.87"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20497-5_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,16]],"date-time":"2022-12-16T12:22:48Z","timestamp":1671193368000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20497-5_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031204968","9783031204975"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20497-5_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"17 December 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CAAI International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cicai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cicai.caai.cn\/#\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"472","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"164","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"35% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.1","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}